Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

adimyth
/
compass-lora-v2

PEFT
Safetensors
lora
decision-model
compass
Model card Files Files and versions
xet
Community

Instructions to use adimyth/compass-lora-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use adimyth/compass-lora-v2 with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B")
    model = PeftModel.from_pretrained(base_model, "adimyth/compass-lora-v2")
  • Notebooks
  • Google Colab
  • Kaggle
compass-lora-v2
122 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
adimyth's picture
adimyth
model card
f31e9b2 verified 5 days ago
  • .gitattributes
    1.52 kB
    initial commit 5 days ago
  • README.md
    597 Bytes
    model card 5 days ago
  • adapter_config.json
    1.22 kB
    compass-lora-v2: LoRA r16 on Qwen3.5-4B 851bf6e8 through the verification/direct readouts; calibration fitted on the hard-like split 5 days ago
  • adapter_model.safetensors
    122 MB
    xet
    compass-lora-v2: LoRA r16 on Qwen3.5-4B 851bf6e8 through the verification/direct readouts; calibration fitted on the hard-like split 5 days ago
  • calibration.json
    1 kB
    compass-lora-v2: LoRA r16 on Qwen3.5-4B 851bf6e8 through the verification/direct readouts; calibration fitted on the hard-like split 5 days ago
  • training.json
    3.38 kB
    compass-lora-v2: LoRA r16 on Qwen3.5-4B 851bf6e8 through the verification/direct readouts; calibration fitted on the hard-like split 5 days ago